# DLR-RM/3DObjectTracking

Algorithms and Publications on 3D Object Tracking

Repository: https://github.com/DLR-RM/3DObjectTracking
Canonical: https://ross.abutalabs.com/products/3dobjecttracking
Language: C++
License: MIT
License Family: permissive
Topics: pose-estimation, computer-vision, accv2020, paper, cvpr2022, ijcv, iros2023, articulated, tpami, real-time, object-tracking, multi-body, multi-modality, rgbd, tracking
Last push: 2025-08-25T09:25:36+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 38, release rhythm 35, longevity 100
- inputs: {"age_days": 2172, "days_push": 373, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1027, forks 182 (observed 2026-08-28T04:03:17.023971+00:00)

## What it is
A collection of C++ implementations of 3D object tracking algorithms from DLR research, including region-based 6DoF trackers (RBGT, SRT3D, ICG, ICG+, Mb-ICG, M3T) that estimate object poses from RGB and depth images. It accompanies peer-reviewed publications and provides code to reproduce their results.

## Use cases
- track 3d objects in real time from rgbd camera frames
- estimate 6dof pose of textureless objects
- track articulated objects and kinematic structures
- robotic perception for object manipulation
- augmented reality object tracking
- reproduce results from published tracking papers

## When to choose
- you need real-time 6DoF pose tracking of known 3D meshes from RGB or RGB-D input
- you want to track articulated or multi-body kinematic structures
- you want research-grade trackers with reproducible paper results
- you are doing robotic manipulation and need object pose feedback

## When to avoid
- you need out-of-the-box detection of unknown objects without a 3D model
- you want a maintained production SDK with long-term support guarantees
- you need a Python-first or deep-learning-based tracker
- your project requires a permissive license beyond MIT obligations

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, robotics, artificial-intelligence
- platform: cpp, cross-platform
- tags: 3d-object-tracking, pose-estimation, 6dof, rgbd, real-time, research-code, articulated-objects, multi-body-tracking, linux

## Member repositories
- DLR-RM/3DObjectTracking (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:17.023971+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:07:50.028218+00:00, confidence not recorded.
  - readme: https://github.com/DLR-RM/3DObjectTracking (fetched 2026-08-28T04:03:17.023971+00:00, sha 920a70f047bd)
- Data as of 2026-08-30T08:39:29.467469+00:00.